library(tidyverse)
## ── Attaching packages ─────────────────── tidyverse 1.2.1 ──
## ✔ ggplot2 3.2.1 ✔ purrr 0.3.3
## ✔ tibble 2.1.3 ✔ dplyr 0.8.3
## ✔ tidyr 1.0.0 ✔ stringr 1.4.0
## ✔ readr 1.3.1 ✔ forcats 0.4.0
## ── Conflicts ────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
library(ggridges)
knitr::opts_chunk$set(
fig.width = 12,
fig.asp = .6,
out.width = "90%"
)
weather_df =
rnoaa::meteo_pull_monitors(c("USW00094728", "USC00519397", "USS0023B17S"),
var = c("PRCP", "TMIN", "TMAX"),
date_min = "2017-01-01",
date_max = "2017-12-31") %>%
mutate(
#create a new variable called "name"
#"NewVarible" = recode("existing variable", "existing values" = "new values" )
name = recode(id, USW00094728 = "CentralPark_NY",
USC00519397 = "Waikiki_HA",
USS0023B17S = "Waterhole_WA"),
tmin = tmin / 10,
tmax = tmax / 10) %>%
select(name, id, everything())
## Registered S3 method overwritten by 'hoardr':
## method from
## print.cache_info httr
## file path: /Users/rachellee/Library/Caches/rnoaa/ghcnd/USW00094728.dly
## file last updated: 2020-01-09 20:48:44
## file min/max dates: 1869-01-01 / 2020-01-31
## file path: /Users/rachellee/Library/Caches/rnoaa/ghcnd/USC00519397.dly
## file last updated: 2020-03-17 01:46:14
## file min/max dates: 1965-01-01 / 2020-03-31
## file path: /Users/rachellee/Library/Caches/rnoaa/ghcnd/USS0023B17S.dly
## file last updated: 2020-03-17 01:46:18
## file min/max dates: 1999-09-01 / 2020-03-31
weather_df
## # A tibble: 1,095 x 6
## name id date prcp tmax tmin
## <chr> <chr> <date> <dbl> <dbl> <dbl>
## 1 CentralPark_NY USW00094728 2017-01-01 0 8.9 4.4
## 2 CentralPark_NY USW00094728 2017-01-02 53 5 2.8
## 3 CentralPark_NY USW00094728 2017-01-03 147 6.1 3.9
## 4 CentralPark_NY USW00094728 2017-01-04 0 11.1 1.1
## 5 CentralPark_NY USW00094728 2017-01-05 0 1.1 -2.7
## 6 CentralPark_NY USW00094728 2017-01-06 13 0.6 -3.8
## 7 CentralPark_NY USW00094728 2017-01-07 81 -3.2 -6.6
## 8 CentralPark_NY USW00094728 2017-01-08 0 -3.8 -8.8
## 9 CentralPark_NY USW00094728 2017-01-09 0 -4.9 -9.9
## 10 CentralPark_NY USW00094728 2017-01-10 0 7.8 -6
## # … with 1,085 more rows
##############
#SCATTER PLOT#
##############
ggplot(weather_df, aes(x=tmin, y=tmax)) + geom_point()
## Warning: Removed 15 rows containing missing values (geom_point).

#SAME AS
weather_df %>%
ggplot(aes(x=tmin, y=tmax)) + geom_point()
## Warning: Removed 15 rows containing missing values (geom_point).

#save the output of ggplot() to an object
plot_weather = weather_df %>%
ggplot(aes(x=tmin, y=tmax))
##AND THEN modify / print
plot_weather + geom_point()
## Warning: Removed 15 rows containing missing values (geom_point).

######################
#Advanced Scatterplot#
######################
ggplot(weather_df, aes(x = tmin, y=tmax, color=name))+ geom_point(alpha= .5) + #alpha=transparency
geom_smooth(se = FALSE) +
facet_grid(. ~ name) #separate grids for each "name"
## `geom_smooth()` using method = 'loess' and formula 'y ~ x'
## Warning: Removed 15 rows containing non-finite values (stat_smooth).
## Warning: Removed 15 rows containing missing values (geom_point).

ggplot(weather_df, aes(x = date, y = tmax, color = name)) +
geom_point(aes(size = prcp), alpha = .5) +
geom_smooth(se = FALSE) +
facet_grid(. ~ name)
## `geom_smooth()` using method = 'loess' and formula 'y ~ x'
## Warning: Removed 3 rows containing non-finite values (stat_smooth).
## Warning: Removed 3 rows containing missing values (geom_point).

###################################################
# Learning Assessment: Write a code chain that starts # with weather_df; focuses only on Central Park,
# converts temperatures to Fahrenheit, makes a
# scatterplot of min vs. max temperature, and overlays # a linear regression line (using options in
# geom_smooth())
###################################################
weather_df %>%
#filtering data with only "CentralPark_NY"
filter(name == "CentralPark_NY") %>%
#adding farenheit variables
mutate( tmax_f = tmax* (9/5) + 32,
tmin_f = tmin* (9/5) + 32) %>%
#plot tmin_f against tmax_f
ggplot( aes (x = tmin_f, y = tmax_f )) +
#adding point
geom_point( alpha = 0.5 ) +
#adding linear regression line
geom_smooth( method = "lm", se = FALSE )

#Smooth Curve
#same plots
ggplot(weather_df, aes(x = date, y=tmax, color = name)) + geom_smooth(se = FALSE)
## `geom_smooth()` using method = 'loess' and formula 'y ~ x'
## Warning: Removed 3 rows containing non-finite values (stat_smooth).

ggplot(weather_df) + geom_smooth( aes (x=date, y=tmax, color = name), se = FALSE)
## `geom_smooth()` using method = 'loess' and formula 'y ~ x'
## Warning: Removed 3 rows containing non-finite values (stat_smooth).

#Scatter Plots
#why are these two different?
ggplot(weather_df) +
geom_point(aes(x=tmax, y=tmin), color = "blue") #--> Defines the color of the point (OUTSIDE aes)
## Warning: Removed 15 rows containing missing values (geom_point).

ggplot(weather_df) +
geom_point(aes(x=tmax, y=tmin, color = "blue")) #--> Creating a new variable called "color" and assigning the value "blue"
## Warning: Removed 15 rows containing missing values (geom_point).

#Histogram
ggplot(weather_df, aes(x = tmax)) +
geom_histogram()
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## Warning: Removed 3 rows containing non-finite values (stat_bin).

ggplot(weather_df, aes(x = tmax, fill = name)) +
geom_histogram(position = "dodge" , binwidth = 2)
## Warning: Removed 3 rows containing non-finite values (stat_bin).

#Density Curve
ggplot(weather_df, aes(x = tmax)) +
geom_density(alpha = .4, adjust = .5, color = "blue")
## Warning: Removed 3 rows containing non-finite values (stat_density).

ggplot(weather_df, aes(x = tmax, fill = name)) +
geom_density(alpha = .4, adjust = .5, color = "blue")
## Warning: Removed 3 rows containing non-finite values (stat_density).

#boxplots
ggplot(weather_df, aes(x = name, y = tmax)) +
geom_boxplot()
## Warning: Removed 3 rows containing non-finite values (stat_boxplot).

#violin plots
ggplot(weather_df, aes(x = name, y = tmax)) +
geom_violin(aes(fill = name), color = "blue", alpha = .5) + stat_summary(fun.y = median, geom = "point", color = "blue", size = 4 )
## Warning: Removed 3 rows containing non-finite values (stat_ydensity).
## Warning: Removed 3 rows containing non-finite values (stat_summary).

#ridge plots
ggplot(weather_df, aes(x = tmax, y = name)) + geom_density_ridges(scale = .85)
## Picking joint bandwidth of 1.84
## Warning: Removed 3 rows containing non-finite values (stat_density_ridges).

#learning assessment
#histogram
ggplot(weather_df, aes( x = prcp, fill = name)) +
geom_histogram(position = "dodge", binwidth = 80)
## Warning: Removed 3 rows containing non-finite values (stat_bin).

#density curve: these two are the same thing
ggplot(weather_df, aes( x = prcp, fill = name)) +
geom_density(alpha = .4, adjust = 40, color = "blue")
## Warning: Removed 3 rows containing non-finite values (stat_density).

ggplot(weather_df, aes( x = prcp)) +
geom_density(aes(fill = name), alpha = .5, adjust = 40)
## Warning: Removed 3 rows containing non-finite values (stat_density).

#ridge plot
ggplot(weather_df, aes( x = prcp, y = name)) +
geom_density_ridges(scale = .85)
## Picking joint bandwidth of 4.61
## Warning: Removed 3 rows containing non-finite values (stat_density_ridges).

#boxplot
ggplot(weather_df, aes(x = name, y = prcp)) + geom_boxplot()
## Warning: Removed 3 rows containing non-finite values (stat_boxplot).

weather_df %>%
filter(prcp > 0) %>%
ggplot(aes(x = prcp, y = name)) +
geom_density_ridges(scale = .85)
## Picking joint bandwidth of 19.7

############################
#Saving and embedding plots#
############################
weather_plot = ggplot(weather_df, aes(x = tmin, y = tmax)) +
geom_point(aes(color = name), alpha = 0.5)
ggsave("weather_plot.pdf", weather_plot, width = 8, height = 5)
## Warning: Removed 15 rows containing missing values (geom_point).